An improved teaching-learning-based optimization (TLBO) algorithm based on hybrid learning strategies and disturbance was proposed to improve the searching functions of the algorithm and solve the problem of being easy to fall into local optima. The mutation strategy of differential evolution algorithm was merged into the learning part of the algorithm, and a hybrid learning strategy was propased to improve the learning ability of students in the later learning as well as the convergence performance of the algorithm. A new disturbance strategy was constructed in the late stage to reduce the possibility of trapping into local optima and ensure global optimality. Experimental results based on the standard test function demonstrate that the proposed algorithm can effectively increase the convergence speed and accuracy and significantly advance the optimization compared with the current similar four kinds of algorithms with excellent performance.
BI Xiao-jun, WANG Jia-hui. Teaching-learning-based optimization algorithm with hybrid learning strategy. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(5): 1024-1031.
参考文献(References):
[1] RAO R V, SAVSANI V J, VAKHARIA D P. Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems [J]. Computer-aid Design, 2011, 43 (3): 303-315.
[2] RAO R V, PATEL V. Multi-objective optimization of heat exchangers using a modified teaching-learning-based optimization algorithm [J]. Applied Mathematical Modelling, 2013, 37(3): 1147-1162.
[3] ZOU F, WANG L, HEI X H, et al. Teachinglearningbased optimization with dynamic group strategy for global optimization [J]. Information Sciences, 2014, 273: 112-131.
[4] 俞欢军,张丽平,陈德钊,等.基于反馈策略的自适应粒子群优化算法[J].浙江大学学报:工学版,2005, 39(9): 12861291.
YU Huan-jun, ZHANG Li-ping, CHEN De-zhao, et al. Adaptive particle swarm optimization algorithm based on feedback mechanism [J]. Journal of Zhejiang University: Engineering Science, 2005, 39(9): 1286-1291.
[5] ZOU F, CHEN D, WANG J T. An improved teaching-learning-based optimization with the social character of pso for global optimization [J]. Computational Intelligence & Neuroscience, 2016, 2016(2): 1-10.
[6] 高立群,欧阳海滨,孔祥勇,等.带有交叉操作的教-学优化算法[J].东北大学学报:自然科学版,2014, 35(3): 323-327.
GAO Li-qun, OUYANG Hai-bin, KONG Xiang-yong, et al. Teaching-learning based optimization algorithm with crossover operation [J]. Journal of Northeastern University :Natural Science, 2014,35(3): 323-327.
[7] 李会荣,乔希民,赵鹏军.融合差分变异的教-学优化算法[J].计算机工程与应用,2016,52(5): 36-40.
LI Hui-rong, QIAO Xi-min, ZHAO Peng-jun. Teaching-learning-based optimization algorithm by using differential mutation [J]. Computer Engineering and Applications, 2016, 52(5): 36-40.
[8] CHEN D B, ZOU F, LI Z, et al. An improved teaching-learning-based optimization algorithm for solving global optimization problem [J]. Information Sciences, 2015, 297: 171-190.
[9] 刘前进,许慧铭,施超,等.改进教与学方法在电力系统无功优化中的应用研究[J].电力系统保护与控制,2015, 43(9): 82-88.
LIU Qian-jin, XU Hui-ming, SHI Chao, et al. Research on modified teaching-learning algorithm for reactive power optimization [J]. Power System Protection and Control, 2015,43(9): 82-88.
[10] 匡芳君.群智能混合优化算法及其应用研究[D].南京:南京理工大学,2014.
KUANG Fang-jun. Hybridized optimization algorithms of swarm intelligence and their application [D]. Nanjing : Nanjing University, 2014.
[11] CHEN D B, ZOU F, WANG J T, et al. A teaching-learning-based optimization algorithm with producer-scrounger model for global optimization [J]. Soft Computing, 2015, 19(3): 745-762.
[12] PRINCE K, STORN R M, LAMPINEN J A. Differential evolution: a practical approach to global optimization :natural computing series[J]. Natural Computing, 2005, 141(2): 1-24.
[13] DAS S, SUGANTHAN P N. Differential evolution: a survey of the state-of-the-art [J]. IEEE Transactions on Evolutionary Computation, 2011, 15(1): 4-31.
[14] YAO X, LIU Y, LIN G M. Evolutionary programming made faster [J]. IEEE Trans on Evolutionary Computation, 1999, 3(2): 82-102.
[15] SUGANTHAN P N, HANSEN N, LIANG J J, et al. Problem definitions and evaluation criteria for the CEC 2005 special session on real-parameter optimization[R]. Singapore: NanyangTechnological University,2005.
[16] 韩俊英,刘成忠,王联国.动态双子群协同进化果蝇优化算法[J].模式识别与人工智能,2013,26 (11):1057-1067.
HAN Ying-jun, LIU Cheng-zhong, WANG Lian-guo. Dynamic double subgroups cooperative fruit fly optimizationg algorithm [J]. Pattern Recognition and Artificial Intelligence, 2013, 26 (11): 1057-1067.